© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 93869
    Prev
    Next
    INDEX
    Explanations

    affirmations or positive statements about experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymoon
    -0.06
    l
    -0.06
    ie
    -0.06
    fi
    -0.05
    pg
    -0.05
    if
    -0.05
    ISTORY
    -0.05
     preset
    -0.05
     Fork
    -0.05
    cf
    -0.05
    POSITIVE LOGITS
    ần
    0.08
    compass
    0.07
    ãĤ¸ãĤ¢
    0.07
     pathMatch
    0.07
    iyi
    0.07
    ÙĪÛĮد
    0.07
    ãĥ¼ãĥĬ
    0.07
    ools
    0.07
    ónico
    0.07
     SHARES
    0.07
    Activations Density 0.021%

    No Known Activations